1.6.3

• Fix the wrong name in GptModel.class

1.6.2

• Update: update models in GptModel.class
• Deprecated: CreateCompletionRequest will be Deprecated

1.6.1

• Optimize:Now, with the use of System.setProperty, you can easily set properties without the need to manually set them each time a request is created.

Explicitly setting in the request > Setting with System.setProperty > System default value.

System.setProperty("OPENAI_API_KEY",""); // no system default value
System.setProperty("OPENAI_API_ORG","");// no system default value
System.setProperty("OPENAI_API_SERVER",""); // default = https://api.openai.com

1.6.0

• new: The CreateChatCompletionRequest function can now call other functions. For more information on how to call functions, please refer to here
• new: Two new models, gpt_3p5_turbo_0613 and gpt_3p5_turbo_16k, have been added to the GptModel.class
• new: The ChatMessage.class now includes a message function, and a new ChatFunction.class has been added for calling
  functions within the model.

1.5.1

• Optimize: CreateChatCompletionRequest.addMessage can now directly accept ChatMessage as a parameter.

//  Now there are two ways to add a message.
new CreateChatCompletionRequest().addMessage("user","hello");
new CreateChatCompletionRequest().addMessage(ChatMessage.userMessage("hello"));

1.5.0

• New: When using CreateEmbeddingsRequest, if base64Embedding is set to 'true', the returned embedding data format will
  be in base64.
• New: EmbeddingUtil has been added to convert base64 string embeddings to numerical embeddings.

1.4.4

• Optimize:Optimize ChatMessage, now providing several convenient instantiation methods.

ChatMessage.systemMessage("content");
ChatMessage.userMessage("content");
ChatMessage.assistantMessage("content");

1.4.3

• Fix bug:Fixed the issue of mismatched error message for CreateEmbeddingsRequest due to incorrect input settings.

Fix bug

• Fix bug:Fix the issue of incorrect formatting of the returned result when using CreateChatCompletionRequest and
  CreateCompletionRequest with stream set to true.

Optimize: Custom server address

In order to facilitate users who need to use proxies, all requests now support self-specifying a server address.